• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.164-169
• /
• 2003

The purpose of this study is to develop a practical image inspect ion system that could recognize it correctly, endowing flexibility to the productive field, although the same object for work will be changed in the size and rotated. In this experiment, it selected a fighter, rotating the direction from 30$^{\circ}$ to 45 simultaneously while changing the size from 1/4 to 1/16, as an object inspection without using another hardware for exclusive image processing. The invariant moments, Hu has suggested, was used as feature vector moment descriptor. As a result of the experiment, the image inspect ion system developed from this research was operated in real-time regardless of the chance of size and rotation for the object inspection, and it maintained the correspondent rates steadily above from 94％ to 96％. Accordingly, it is considered as the flexibility can be considerably endowed to the factory automat ion when the image inspect ion system developed from this research is applied to the product ive field.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.112-123
• /
• 1994

In this paper, inspection and subpixed alignment algorithms of SMD's (Surface Mounting Devices) using fuzzy morphology are proposed. First, camera calibration is performed and then the inspection algorithm detects defects such as lead bending and breaking using the ruler generated by fuzy morphology. The SMD having no defects is tested whether it is mounted in the specified position or not. The proposed subpixel alignment algorithm detects accurately orientation and position using subpixel interpolation. It consists of two parts: preprocessing and main processing steps, in which corner points and coarse orientation of a SMD are detected, and interpolation is used to obtain final parameters with wubpixel accuracy. The computer simulation shows that the proposed algorithms give more accurate parameters, and they can be applied to fast and accurate automatic surface mounting systems.

• Proceedings of the KWS Conference
• /
• 2004.05a
• /
• pp.305-307
• /
• 2004

One set of rotor coils is required per each large generator rotor assembly, Rotors consist of two directly opposing poles. Each pole requires from 5 to 9 coils. Each coil is made up of two halves identified on the connection end. These coil halves will be joined together by butt brazing process during subsequent rotor assembly. Each half coil is made up of typically 4 to 9 layers of copper conductors. Because of Generator rotor is rotated very high speed with 3,600RPM, the quality soundness of brazed joints is very important at each coil. But, it is very difficult to be optimized non-destructive evaluation, because c-coil has the long shape and evaluation is to be done assembled condition. In this paper introduce newly developed inspection process and acceptance standards for the ultrasonic inspection of " C" coil butt braze. This inspection system is a semi-automatic ultrasonic flaw detector with data acquisition and retention capable of assessing the relative lack of bond of brazed butt joints

• Journal of Biosystems Engineering
• /
• v.23 no.6
• /
• pp.621-628
• /
• 1998

In order to develop an inspection algorithm for an automatic eggshell inspection system, acoustic impulse response with neural network method was studied. An improved error backpropagation algorithm was selected as a loaming rule of neural network, and three layer network was chosen for the neural network architecture. Acoustic signals in time domain and theirs power spectrum were studied as the input to the neural network. The classification feasibility and success rate were investigated in terms of statistical analysis and neural network approach. As a result, the success rate was 95% with the statistical model having five independent variables. Among the neural network models studied, the power spectrum of acoustic signal as the input with 64 input neurons and the two impact data showed the success rate of 95.5% which was slightly higher than of statistical analysis.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.61-62
• /
• 2006

A new neural network classifier is proposed for the automatic real-time surface inspection of high-speed cold steel strips having 11 different types of defects. 46 geometrical and gray-level features are extracted for the defect classification. 3241 samples of Posco's Kwangyang steel factory are used for training and testing the neural network classifier. The developed classifier produces plausible 15% error rate which is much better than 20-30% error rate of human vision inspection adopted in most of domestic steel factories.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.4 s.193
• /
• pp.76-83
• /
• 2007

A new neural network classifier is proposed for the automatic real-time surface inspection of high-speed cold steel strips having 11 different types of defects. 46 geometrical and gray-level features are extracted for the defect classification. 3241 samples of Posco's Kwangyang steel factory are used for training and testing the neural network classifier. The developed classifier produces plausible 15% error rate which is much better than 20-30% error rate of human vision inspection adopted in most of domestic steel factories.

• Journal of the Korean Society of Industry Convergence
• /
• v.18 no.4
• /
• pp.241-249
• /
• 2015

The purpose of this research is to develop the pattern recognition algorithm based on smart camera for inspection automation, and including external surface state of molding parts or optical parts. By performance verification, this development can be applied to establish for existing reflex data because inputting surface badness degree of scratch's standard specification condition directly. And it is pdssible to distinguish from schedule error of badness product and normalcy product within schedule extent after calculating the error comparing actuality measurement reflex data and standard reflex data mutually. The proposed technology cab be applied to test for masearing of the smallest 10 pixel unit. It is illustrated the relibility pf proposed technology by an experiment.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.959-962
• /
• 1988

This paper describes an automatic visual inspection system for fabric defects based on pattern recognition techniques. The inspection for fabric defects can be separated into three sequences of operations which are the detection of fabric defects[1], the classification of figures of fabric defects, and the classification of fabric defects. Comparing projections of defect-detected images with the predefined complex, the classification accuracy of figures of fabric defects was found to be 95.3 percent. Employing the Bayes classifier using cluster shade in SGLDM and variance in decorrelation method as features, the classification accuracy of regional figure defects was found to be 82.4 percent. Finally, some experimental results for line and dispersed figures of fabric defects are included.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.361-362
• /
• 2006

Magnetic Flux Leakage (MFL) inspection is a general non-destructive testing (NDT) method to detect the corrosion of natural gas pipelines. Currently, it is subjectively analyzed by trained analysts. In spite of investing much time and human resources, the inspection results may be different according to the analysts' expertise. So, many gas suppliers are keenly interested in the automation of the interpretation process. This paper presents a Gaussian variance filtering method of MFL signals, which is taken from MFL pigging of underground pipelines. In the proposed algorithm the original MFL signals are filtered by multiple Gaussians with different variance. Experimental results show that this approach does not need to align bias and to use explicit noise reduction algorithm.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.333-334
• /
• 2007

We propose a path planning method to decrease a inspection lead time of line scan camera in SMT(surface mount technology) in-line system. The inspection window area of printed circuit board should be minimized to consider the FOV(field of view) of line scan camera so that line scan inspector is going to find a optimal solution of path planning. We propose one of the hierarchical clustrering algorithm for a given board. Comparative simulation results are presented to verify the usefulness of proposed method.